INDEX

Explanations

references to terrorism and organizations associated with it

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rzej

-0.49

 الحره

-0.49

 âmes

-0.48

 FBref

-0.48

GeoNames

-0.47

 AttributeSet

-0.44

 Souver

-0.43

 Hippo

-0.43

wärts

-0.43

ciaio

-0.43

POSITIVE LOGITS

 terrorist

1.03

terror

0.93

 terror

0.88

 terrorists

0.86

 recruiting

0.85

 terrorism

0.84

 recruitment

0.83

 Terror

0.81

 extremist

0.78

 recruited

0.77

Activations Density 0.480%

references to terrorism and organizations associated with it

No Comments

No Known Activations